© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 77827
    Prev
    Next
    INDEX
    Explanations

    "Pass"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viki
    -0.59
    brokes
    -0.52
    UnknownFieldSet
    -0.51
     ffilm
    -0.50
    persky
    -0.49
     Philippines
    -0.49
     Heaton
    -0.48
    Петер
    -0.48
     leop
    -0.48
    tabler
    -0.47
    POSITIVE LOGITS
     Passage
    0.75
     PASS
    0.63
     Pass
    0.62
    Passage
    0.61
    Pass
    0.59
    passage
    0.55
     Passes
    0.52
     passagem
    0.52
     passage
    0.49
     pass
    0.49
    Activations Density 0.000%

    No Known Activations